Feasibility of Using AI to Evaluate General Surgery Residency Application Personal Statements
AI applied rubric-based scoring consistently but interpreted narrative content differently than human reviewers. While AI may enhance consistency and scalability in early application screening, its limitations in recognizing implicit meaning suggest human judgment remains essential for evaluating nuanced or inferential content. Caution should be exercised in adopting AI tools for subjective application review.
Authors
- Judith C. French (ORCID: https://orcid.org/0000-0001-8393-8376)
- Ajita S. Prabhu (ORCID: https://orcid.org/0000-0003-1343-9250)
- Andrew Conner (ORCID: https://orcid.org/0000-0001-7246-2317)
- Pooja Varman (ORCID: https://orcid.org/0000-0003-2073-0759)
- Shadae Nicholas (ORCID: https://orcid.org/0000-0001-6720-521X)
- Jeremy M. Lipman (ORCID: https://orcid.org/0000-0001-6165-0304)
Institutions
- Cleveland Clinic (US)
- Cleveland Clinic Lerner College of Medicine (US)
- Case Western Reserve University (US)
Publication Details
- Journal
- Journal of surgical education
- Published
- 2025-08-30
- DOI
- https://doi.org/10.1016/j.jsurg.2025.103655
- Citations
- 3
- Primary Topic
- Diversity and Career in Medicine
- Type
- article
- Field-Weighted Citation Impact
- 11.60
Funders
- Cleveland Clinic